ayyyq/llama2_70b_gsm8k_llama2_7b_iter2_hybrid
Updated
weak-to-strong-reasoning
-
-
ayyyq/llama2_70b_gsm8k_llama2_7b_iter2_hybrid_orpo
Updated -
ayyyq/llama2_70b_gsm8k_gemma_2b_iter2_hybrid
Updated -
ayyyq/llama2_70b_gsm8k_gemma_2b_iter2_hybrid_orpo
Updated -
ayyyq/llama2_70b_gsm8k_mistral_7b_iter2_hybrid
Updated -
ayyyq/llama2_70b_gsm8k_mistral_7b_iter2_hybrid_orpo
Updated -
ayyyq/llama2_70b_math_llama2_7b_iter1_hybrid_orpo
Updated -
ayyyq/llama2_70b_math_gemma_2b_iter1_hybrid_orpo
Updated -
ayyyq/llama2_70b_math_mistral_7b_iter1_hybrid_orpo
Updated